Skip to content

Package Native, Vulkan, and GGML as an executorch-native wheel (#24069) - #24069

Open
JakeStevens wants to merge 2 commits into
pytorch:mainfrom
JakeStevens:export-D126459370
Open

JakeStevens wants to merge 2 commits into
pytorch:mainfrom
JakeStevens:export-D126459370

Conversation

@JakeStevens

@JakeStevens JakeStevens commented Oct 21, 2026 •

Copy link
Copy Markdown
Contributor

Summary:

Add a separately installable Linux SDK wheel containing the Native runtime, Vulkan engine and shaders, and GGML CPU engine. Its CMake package lets consumers build the shipped vision runner without rebuilding the runtime, and the package coexists with executorch.

Keep the standalone wheel recipe in backends/native/python and its Python wrappers alongside the runtime in backends/native/pybindings. CMake installs those sources into executorch_native; the source tree does not need a nested copy of the import package. Python execution bindings are added in the following diff.

Authored with assistance from Codex.

Differential Revision: D126459370

@pytorch-bot pytorch-bot Bot added the module: vulkan Issues related to the Vulkan delegate and code under backends/vulkan/ label Oct 21, 2026
@pytorch-bot

pytorch-bot Bot commented Oct 21, 2026 •

Copy link
Copy Markdown

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24069

Note: Links to docs will display an error until the docs builds have been completed.

❌ 4 Unclassified Failures

As of commit 3dbe48c with merge base 141f543 (image):

UNCLASSIFIED FAILURES - DrCI could not classify the following jobs because the workflow did not run on the merge base. The failures may be pre-existing on trunk or introduced by this PR:

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@meta-cla meta-cla Bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Oct 21, 2026
@meta-codesync

meta-codesync Bot commented Oct 21, 2026

Copy link
Copy Markdown
Contributor

@JakeStevens has exported this pull request. If you are a Meta employee, you can view the originating Diff in D126459370.

@github-actions

Copy link
Copy Markdown

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

@meta-codesync meta-codesync Bot changed the title Package Native, Vulkan, and GGML as an executorch-native wheel Package Native, Vulkan, and GGML as an executorch-native wheel (#24069) Oct 21, 2026
JakeStevens added a commit to JakeStevens/executorch that referenced this pull request Oct 21, 2026
…orch#24069)

Summary:

Add a Linux SDK wheel containing the Native runtime, Vulkan engine and shaders, and GGML CPU engine. Its CMake package lets consumers build the shipped vision runner without rebuilding the runtime. The separate package coexists with `executorch`; Python execution bindings remain out of scope.

Authored with assistance from Codex.

Differential Revision: D126459370
JakeStevens added a commit to JakeStevens/executorch that referenced this pull request Oct 21, 2026
…orch#24069)

Summary:

Add a Linux SDK wheel containing the Native runtime, Vulkan engine and shaders, and GGML CPU engine. Its CMake package lets consumers build the shipped vision runner without rebuilding the runtime. The separate package coexists with `executorch`; Python execution bindings remain out of scope.

Authored with assistance from Codex.

Differential Revision: D126459370
Summary:

Extend the shared `FuseBatchNormWithConvPass` to fold frozen evaluation BatchNorm during Native AOT export, using a thin `ExportedProgram` adapter in Native's default pass pipeline. Preserve existing `GraphModule` callers and grouped/transposed convolution support.

Functionalize all methods before collecting mutable buffers. This protects running statistics updated by another `.ptn` method while allowing folding through `ReLU(inplace=True)`. 


Authored with assistance from Codex.

Differential Revision: D126696057
…orch#24069)

Summary:

Add a separately installable Linux SDK wheel containing the Native runtime, Vulkan engine and shaders, and GGML CPU engine. Its CMake package lets consumers build the shipped vision runner without rebuilding the runtime, and the package coexists with `executorch`.

Keep the standalone wheel recipe in `backends/native/python` and its Python wrappers alongside the runtime in `backends/native/pybindings`. CMake installs those sources into `executorch_native`; the source tree does not need a nested copy of the import package. Python execution bindings are added in the following diff.

Authored with assistance from Codex.

Differential Revision: D126459370
JakeStevens added a commit to JakeStevens/executorch that referenced this pull request Oct 21, 2026
…orch#24069)

Summary:
Pull Request resolved: pytorch#24069

Add a separately installable Linux SDK wheel containing the Native runtime, Vulkan engine and shaders, and GGML CPU engine. Its CMake package lets consumers build the shipped vision runner without rebuilding the runtime, and the package coexists with `executorch`.

Keep the standalone wheel recipe in `backends/native/python` and its Python wrappers alongside the runtime in `backends/native/pybindings`. CMake installs those sources into `executorch_native`; the source tree does not need a nested copy of the import package. Python execution bindings are added in the following diff.

Authored with assistance from Codex.

Differential Revision: D126459370

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. meta-exported module: vulkan Issues related to the Vulkan delegate and code under backends/vulkan/

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant